Energy expenditure estimation can be used to measure the exercise load and physical condition of different individuals, such as soldiers, athletes, firemen, etc., during their training and work. Energy expenditure est...Energy expenditure estimation can be used to measure the exercise load and physical condition of different individuals, such as soldiers, athletes, firemen, etc., during their training and work. Energy expenditure estimation methods based on computer vision have rapidly developed in recent years. Compared with sensor-based methods, such methods are capable of monitoring several target persons at the same time, and the subjects do not need to wear different sensor devices that hamper their movement. In this paper, we propose a cross-attention spatial–temporal convolutional neural network to predict the energy expenditure of people under different exercise intensities. The model explores the relationship between changes in the human skeleton and energy expenditure intensity. In addition, a cross-attention correction module is used to reduce the negative effects of individual physical fitness characteristics during energy expenditure estimation. The experimental results show that our proposed method achieves high accuracy for energy expenditure estimation and performs better than existing computer vision-based energy expenditure estimation methods do. The proposed method can be widely used in various physical activity scenarios to measure energy expenditure, increasing the convenience of usage.展开更多
In China,soft plastic pots are the predominant container used for the cultivation of citrus seedlings.However,due to their soft characteristics,manual operation is the primary method of pot filling and placement,which...In China,soft plastic pots are the predominant container used for the cultivation of citrus seedlings.However,due to their soft characteristics,manual operation is the primary method of pot filling and placement,which significantly impedes production efficiency.In order to resolve this issue,a solution for filling citrus seedling pots based on a turnover box was proposed.By analyzing the movement status of the turnover box unloading mechanism,the length of each component was calculated,and the specific structure of the turnover box was designed.The substrate lifting rate of the conveyor belt was analyzed and the structural parameters of the lifting mechanism were determined.Through theoretical analysis of the substrate trajectory during the dispersion process,the inlet position of the splitter mechanism was determined,and the specific structure of the splitter mechanism was designed to control the uniformity of the substrate distribution.A seedling pot filling process simulation model was constructed using discrete element software.The operating parameters of the filling device were evaluated,and the filling effect was analyzed.The test prototype was processed and three loading tests were carried out.The results show that the prototype runs stably,with a loading time of 8 s for 16 pots.The unloading mechanism of the turnover box is reliable,and the seedling pots are neatly arranged after unloading.The maximum weight among the 16 pots in the turnover box is 2.00 kg,while the minimum weight is 1.88 kg.The mean weight is 1.94 kg,with a coefficient of variation of 2.47%.The excess substrate mass scraped on the turnover box is 0.83 kg,accounting for 2.67%of the total mass of the 16 pots.The prototype design is reasonable,with good filling uniformity and high efficiency.The research results can provide reference for the development and optimization of citrus seedling pot filling and transportation equipment in the future.展开更多
Compared with manual sorting of citrus fruit,vision-based sorting solutions can help achieve higher accuracy and efficiency.In this study,we present a vision system based on CNN-LSTM,which can cooperate with robotic g...Compared with manual sorting of citrus fruit,vision-based sorting solutions can help achieve higher accuracy and efficiency.In this study,we present a vision system based on CNN-LSTM,which can cooperate with robotic grippers for real-time sorting and is readily applicable to various citrus processing plants.A CNN-based detector was adopted to detect the defective oranges in view and temporarily classify them into corresponding types,and an LSTM-based predictor was used to predict the position of the oranges in a future frame based on image sequential data.The fusion of CNN and LSTM networks enabled the system to track defective ones during rotation and identify their true types,and their future path was also predicted which is vital for predictive control of visually guided robotic grasping.High detection accuracy of 94.1%was obtained based on experimental results,and the error for path prediction was within 4.33 pixels 40 frames later.The average time to process a frame was between 28 and 62 frames per second,which also satisfied real-time performance.The results proved the potential of the proposed system for automated citrus sorting with good precision and efficiency,and it can be readily extended to other fruit crops featuring high versatility.展开更多
To solve the problems of the traditional orchard conveyor,such as inflexible steering,a complex structure,poor stability and no power grid coverage,a remote-controlled rail conveyor powered by hydraulic pressure for m...To solve the problems of the traditional orchard conveyor,such as inflexible steering,a complex structure,poor stability and no power grid coverage,a remote-controlled rail conveyor powered by hydraulic pressure for mountainous orchards was designed and manufactured.Climbing stress analysis was carried out on a full-load trailer to obtain the maximum traction force,which met the requirement of the climbing slope of the transport mechanism.The key components of the conveyor were developed,such as the hydraulic transmission,the control system,safety protection devices,limiting devices,the throttle and decompression actuator,the counterweight tension and the battery.Through the theoretical calculations of key components,an orchard conveyor powered by diesel and hydraulic pressure was designed.Finally,the working performance of the transporter was tested through functionality,driving speed,system pressure and remote-controlled tests.The test results showed that the climbing angle of the transporter can reach 50°,the uphill load can reach 840 kg,the downhill load can reach 1100 kg,and the average running speed is 0.77 m/s;the driving speed ranges from 0.29 m/s to 1.08 m/s,and the system pressure ranges from 3.2 MPa to 10 MPa.The driving speed and system pressure are significantly affected by the load,and the remote control distance can reach 455 m.The technical specifications of the transporter meet all the design requirements,and the problem of stable operation of the transporter without power grid coverage has been addressed.The research results can well meet the practical application requirements of mountain orchard transportation without power grid coverage and provide theoretical reference for the design of key components of mountain orchard transportation machinery.展开更多
The traditional technology for internal quality detection of citrus fruit is believed to be destructive,inefficient,and error-prone.To address these issues,a novel method has been developed to evaluate nondestructivel...The traditional technology for internal quality detection of citrus fruit is believed to be destructive,inefficient,and error-prone.To address these issues,a novel method has been developed to evaluate nondestructively the sugar-acid ratio(SAR)of soluble solids by using the oil glands density(OGD).In this study,a total of 584 samples with different widths were collected.The sample data were correlated that the SAR and OGD decreased with time during storage.The relevance with time was significant between SAR and OGD of citrus positively correlated in the calibration group(R2=0.82),which indicated that OGD could be used to predict the internal quality of citrus.It indicated that a new generation of digital microscopy could provide an alternative to predict nondestructively the internal quality of citrus fruit,as well as some theoretical insight for further studies of online quality detection in the future.展开更多
In order to address the problem of citrus seedling pot filling and transporting which is time-consuming and labor-intensive in China,a scheme for seedling pot filling and placing was proposed,and a self-propelled citr...In order to address the problem of citrus seedling pot filling and transporting which is time-consuming and labor-intensive in China,a scheme for seedling pot filling and placing was proposed,and a self-propelled citrus seedling pot filling and placing machine was designed which can fill and place 48 pots at one time.Firstly,the rotary hopper door mechanism was designed,the movement of the hopper door was analyzed,and the connection between the opening size and the movement time of the hopper door was determined.Then,the transmission system of the machine was designed,the power consumption of the hopper movement and substrate stirring were calculated,and the power requirement of the transmission system was determined.The lifting structure of the seedling pots frame was analyzed,the size of the flipping structure of the cover plate was calculated,and the seedling pots frame was designed.After that,the substrate flow rate curve was measured through the substrate flow rate experiments,and the hopper-controlled movement speed was calculated.Furthermore,the experimental prototype was manufactured and tested.The test results indicate that the filling number of pots was 48 one time,the filling time was 30 s,and the seedling pots were fully filled and placed in order.The average filling mass of the seedling pots was 2.23 kg,and the average mass variation coefficient was 2.7%.The substrate mass which is scraped out is 0.81 kg,accounting for 0.76%of the total filling mass at one time.This designed machine had a reasonable structure and high filling efficiency.The reseach can provide a reference for the development and optimization of the citrus seedling pots filling and transporting machine.展开更多
In order to solve the problems of complexity of control systems and the limited power supply of traditional fuelpowered and battery-driven transporters operating in mountainous orchards,a sliding contact line-powered ...In order to solve the problems of complexity of control systems and the limited power supply of traditional fuelpowered and battery-driven transporters operating in mountainous orchards,a sliding contact line-powered track transporter was designed and manufactured based on theoretical calculations.Key components of the transporter were developed such as a PLC-based(programmable logic controller)control system,a sliding contact power supply,and transmission system,and a position limit device.The functions and performance of designed transporter were tested.The test results showed that the transporter exhibited a high stability of operation with an average operation velocity of 0.70 m/s,the maximum working slope of 48°,the maximum load of 400 kg,and the maximum remote control distance reaching 1482 m.When the power supply circuit of sliding contact line was 108.8 m in length,the maximum voltage drop was 2.4 V,and the maximum power loss was 174.72 W,which were close to the theoretical calculation values.With a single power supply cabinet,the transporter can operate normally for a maximum track distance of 175.69 m.All the technical indicators of the transporter met the design requirements,and the above-mentioned problems such as complexity of the control system and limited energy supply of the traditional mountain orchard transporter were well solved.This study can provide reference for the design and optimization of mountain orchard transporter.展开更多
3D phenotyping of the external and internal structures is important to breed new fruit species.As manual phenotyping is error-prone and time-consuming,developing high-throughput solutions with enhanced precision and l...3D phenotyping of the external and internal structures is important to breed new fruit species.As manual phenotyping is error-prone and time-consuming,developing high-throughput solutions with enhanced precision and low costs is necessary.This study presents CitrusGAN,a generative adversarial network-based method to reconstruct 3D citrus CT models from sparse-view X-ray images.The input X-rays are arranged in orthogonal pairs to provide additional information,and customized loss functions enable more effective learning of the mapping from 2D X-ray features to 3D CT volumes.Experimental results show that 6 views can generate high-quality citrus CT volumes,with a structural similarity index of 92.1%and a peak signal-to-noise ratio of 26.374 dB compared with the real CT models.Moreover,the morphology of the generated model can be conveniently measured in the 3D space,facilitating the extraction of phenotypic traits including fruit length,width,height,volume,surface area,peel thickness,number of segments,and edible rate with high precision.As X-rays can be obtained using low-cost X-ray machines with high efficiency,the proposed method can be potentially developed into high-throughput equipment for fruit production lines or portable devices to realize in-field phenotyping.展开更多
In order to study the influence rule of various factors on the operating power consumption of the traction orchard transporter and realize the optimal design of the operation power consumption of the transporter,accor...In order to study the influence rule of various factors on the operating power consumption of the traction orchard transporter and realize the optimal design of the operation power consumption of the transporter,according to the traditional experience and the existing research foundation,the monorail transporter test bench was designed and built on the basis of the whole structure and operation characteristics of the transporter.Taking the motor frequency,track gradient and load as the investigation factors,and the driving shaft power,shaft power transmission and mechanical efficiency as the evaluation indices,the orthogonal test was conducted,and the range analysis of the influence effect was carried out according to the test results.The primary and secondary orders of the influence of various factors were obtained that motor frequency was greater than track gradient and track gradient was greater than load.According to the orthogonal test results,the second-order response surface method was used to establish the optimization model of the power consumption of the transporter,and the model was verified on the test bench.The results showed that the relative error between the model optimization value and the test value based on the response surface power optimization model was less than 10%,which indicated that the power optimization model had satisfactory performance.The research can provide a reference for the orchard conveyor to choose the parameter combination which can save power consumption and the motor that matches power consumption.展开更多
基金supported by the National Key Research and Development Program of China (Grant No.2022YFC3600403)Emerging Interdisciplinary Platform for Medicine and Engineering in Sports (EIPMES),Beijing,China。
文摘Energy expenditure estimation can be used to measure the exercise load and physical condition of different individuals, such as soldiers, athletes, firemen, etc., during their training and work. Energy expenditure estimation methods based on computer vision have rapidly developed in recent years. Compared with sensor-based methods, such methods are capable of monitoring several target persons at the same time, and the subjects do not need to wear different sensor devices that hamper their movement. In this paper, we propose a cross-attention spatial–temporal convolutional neural network to predict the energy expenditure of people under different exercise intensities. The model explores the relationship between changes in the human skeleton and energy expenditure intensity. In addition, a cross-attention correction module is used to reduce the negative effects of individual physical fitness characteristics during energy expenditure estimation. The experimental results show that our proposed method achieves high accuracy for energy expenditure estimation and performs better than existing computer vision-based energy expenditure estimation methods do. The proposed method can be widely used in various physical activity scenarios to measure energy expenditure, increasing the convenience of usage.
基金supported by Central University Independent Innovation Fund Project“Key Technologies on Intelligent Filling and Transportation Platform for Citrus Seedling”(Grant No.2662024GXPY014).
文摘In China,soft plastic pots are the predominant container used for the cultivation of citrus seedlings.However,due to their soft characteristics,manual operation is the primary method of pot filling and placement,which significantly impedes production efficiency.In order to resolve this issue,a solution for filling citrus seedling pots based on a turnover box was proposed.By analyzing the movement status of the turnover box unloading mechanism,the length of each component was calculated,and the specific structure of the turnover box was designed.The substrate lifting rate of the conveyor belt was analyzed and the structural parameters of the lifting mechanism were determined.Through theoretical analysis of the substrate trajectory during the dispersion process,the inlet position of the splitter mechanism was determined,and the specific structure of the splitter mechanism was designed to control the uniformity of the substrate distribution.A seedling pot filling process simulation model was constructed using discrete element software.The operating parameters of the filling device were evaluated,and the filling effect was analyzed.The test prototype was processed and three loading tests were carried out.The results show that the prototype runs stably,with a loading time of 8 s for 16 pots.The unloading mechanism of the turnover box is reliable,and the seedling pots are neatly arranged after unloading.The maximum weight among the 16 pots in the turnover box is 2.00 kg,while the minimum weight is 1.88 kg.The mean weight is 1.94 kg,with a coefficient of variation of 2.47%.The excess substrate mass scraped on the turnover box is 0.83 kg,accounting for 2.67%of the total mass of the 16 pots.The prototype design is reasonable,with good filling uniformity and high efficiency.The research results can provide reference for the development and optimization of citrus seedling pot filling and transportation equipment in the future.
基金National Key R&D Program(2020YFD1000101)and Special Funds for the Construction of Industrial Technology System of Modern Agriculture(Citrus)(CARS-26)Construction Project of Citrus Whole Course Mechanized Scientifific Research Base(Agricultural Development Facility 297[2017]19),Hubei Agricultural Science and Technology Innovation Action Project.
文摘Compared with manual sorting of citrus fruit,vision-based sorting solutions can help achieve higher accuracy and efficiency.In this study,we present a vision system based on CNN-LSTM,which can cooperate with robotic grippers for real-time sorting and is readily applicable to various citrus processing plants.A CNN-based detector was adopted to detect the defective oranges in view and temporarily classify them into corresponding types,and an LSTM-based predictor was used to predict the position of the oranges in a future frame based on image sequential data.The fusion of CNN and LSTM networks enabled the system to track defective ones during rotation and identify their true types,and their future path was also predicted which is vital for predictive control of visually guided robotic grasping.High detection accuracy of 94.1%was obtained based on experimental results,and the error for path prediction was within 4.33 pixels 40 frames later.The average time to process a frame was between 28 and 62 frames per second,which also satisfied real-time performance.The results proved the potential of the proposed system for automated citrus sorting with good precision and efficiency,and it can be readily extended to other fruit crops featuring high versatility.
基金The authors acknowledge that this work was supported by the National Key R&D Program(Grant No.2020YFD1000101)Special Funds for the Construction of Industrial Technology System of Modern Agriculture(Citrus)(Grant No.CARS-26)+2 种基金Construction Project of Citrus Whole Course Mechanized Scientific Research Base(Agricultural Development Facility[2017]19)Hubei Agricultural Science and Technology Innovation Action Project,Young Innovative Talents Project of General Colleges and Universities in Guangdong Province(Grant No.2018KQNCX311)Science and Technology Program of Guangdong Polytechnic College(Grant No.JXGG202030).
文摘To solve the problems of the traditional orchard conveyor,such as inflexible steering,a complex structure,poor stability and no power grid coverage,a remote-controlled rail conveyor powered by hydraulic pressure for mountainous orchards was designed and manufactured.Climbing stress analysis was carried out on a full-load trailer to obtain the maximum traction force,which met the requirement of the climbing slope of the transport mechanism.The key components of the conveyor were developed,such as the hydraulic transmission,the control system,safety protection devices,limiting devices,the throttle and decompression actuator,the counterweight tension and the battery.Through the theoretical calculations of key components,an orchard conveyor powered by diesel and hydraulic pressure was designed.Finally,the working performance of the transporter was tested through functionality,driving speed,system pressure and remote-controlled tests.The test results showed that the climbing angle of the transporter can reach 50°,the uphill load can reach 840 kg,the downhill load can reach 1100 kg,and the average running speed is 0.77 m/s;the driving speed ranges from 0.29 m/s to 1.08 m/s,and the system pressure ranges from 3.2 MPa to 10 MPa.The driving speed and system pressure are significantly affected by the load,and the remote control distance can reach 455 m.The technical specifications of the transporter meet all the design requirements,and the problem of stable operation of the transporter without power grid coverage has been addressed.The research results can well meet the practical application requirements of mountain orchard transportation without power grid coverage and provide theoretical reference for the design of key components of mountain orchard transportation machinery.
基金supported in part by the National Key R&D Projects of China(Grant No.2017YFD0701405)and the Earmarked Fund for Modern Agro-industry(Citrus)Technology Research System of China(Grant No.CARS-27)+1 种基金and both Special Funds for the Constnuction of Industrial Technology System of Modem Agriculture(Citrus)(CARS 26)and National Key R&D Program(Grant No.2020YFD01000101)the Construction Project of Citrus Whole Course Mechanized Scientific Research Base(Agricultural Development Facility[2017]19),Hubei Agricultural Science and Technology Innovation Action Project.
文摘The traditional technology for internal quality detection of citrus fruit is believed to be destructive,inefficient,and error-prone.To address these issues,a novel method has been developed to evaluate nondestructively the sugar-acid ratio(SAR)of soluble solids by using the oil glands density(OGD).In this study,a total of 584 samples with different widths were collected.The sample data were correlated that the SAR and OGD decreased with time during storage.The relevance with time was significant between SAR and OGD of citrus positively correlated in the calibration group(R2=0.82),which indicated that OGD could be used to predict the internal quality of citrus.It indicated that a new generation of digital microscopy could provide an alternative to predict nondestructively the internal quality of citrus fruit,as well as some theoretical insight for further studies of online quality detection in the future.
基金supported by the Chongqing Research and Development Project‘Key Technology Research and Equipment Development of Intelligent Management for Citrus Seedling Plant’(cstc2019jscx-gksbX0095).
文摘In order to address the problem of citrus seedling pot filling and transporting which is time-consuming and labor-intensive in China,a scheme for seedling pot filling and placing was proposed,and a self-propelled citrus seedling pot filling and placing machine was designed which can fill and place 48 pots at one time.Firstly,the rotary hopper door mechanism was designed,the movement of the hopper door was analyzed,and the connection between the opening size and the movement time of the hopper door was determined.Then,the transmission system of the machine was designed,the power consumption of the hopper movement and substrate stirring were calculated,and the power requirement of the transmission system was determined.The lifting structure of the seedling pots frame was analyzed,the size of the flipping structure of the cover plate was calculated,and the seedling pots frame was designed.After that,the substrate flow rate curve was measured through the substrate flow rate experiments,and the hopper-controlled movement speed was calculated.Furthermore,the experimental prototype was manufactured and tested.The test results indicate that the filling number of pots was 48 one time,the filling time was 30 s,and the seedling pots were fully filled and placed in order.The average filling mass of the seedling pots was 2.23 kg,and the average mass variation coefficient was 2.7%.The substrate mass which is scraped out is 0.81 kg,accounting for 0.76%of the total filling mass at one time.This designed machine had a reasonable structure and high filling efficiency.The reseach can provide a reference for the development and optimization of the citrus seedling pots filling and transporting machine.
基金supported by the Special Funds for the Construction of Industrial Technology System of Modern Agriculture(Citrus)(Grant No.CARS-26)National Key R&D Program(Grant No.2020YFD1000101)Hubei Province Key R&D Program(Grant No.2021BBA091).
文摘In order to solve the problems of complexity of control systems and the limited power supply of traditional fuelpowered and battery-driven transporters operating in mountainous orchards,a sliding contact line-powered track transporter was designed and manufactured based on theoretical calculations.Key components of the transporter were developed such as a PLC-based(programmable logic controller)control system,a sliding contact power supply,and transmission system,and a position limit device.The functions and performance of designed transporter were tested.The test results showed that the transporter exhibited a high stability of operation with an average operation velocity of 0.70 m/s,the maximum working slope of 48°,the maximum load of 400 kg,and the maximum remote control distance reaching 1482 m.When the power supply circuit of sliding contact line was 108.8 m in length,the maximum voltage drop was 2.4 V,and the maximum power loss was 174.72 W,which were close to the theoretical calculation values.With a single power supply cabinet,the transporter can operate normally for a maximum track distance of 175.69 m.All the technical indicators of the transporter met the design requirements,and the above-mentioned problems such as complexity of the control system and limited energy supply of the traditional mountain orchard transporter were well solved.This study can provide reference for the design and optimization of mountain orchard transporter.
基金This work is supported by the National Science Foundation of China(32302206)the Fundamental Research Funds for the Central Universities,China(2662024SZ002).
文摘3D phenotyping of the external and internal structures is important to breed new fruit species.As manual phenotyping is error-prone and time-consuming,developing high-throughput solutions with enhanced precision and low costs is necessary.This study presents CitrusGAN,a generative adversarial network-based method to reconstruct 3D citrus CT models from sparse-view X-ray images.The input X-rays are arranged in orthogonal pairs to provide additional information,and customized loss functions enable more effective learning of the mapping from 2D X-ray features to 3D CT volumes.Experimental results show that 6 views can generate high-quality citrus CT volumes,with a structural similarity index of 92.1%and a peak signal-to-noise ratio of 26.374 dB compared with the real CT models.Moreover,the morphology of the generated model can be conveniently measured in the 3D space,facilitating the extraction of phenotypic traits including fruit length,width,height,volume,surface area,peel thickness,number of segments,and edible rate with high precision.As X-rays can be obtained using low-cost X-ray machines with high efficiency,the proposed method can be potentially developed into high-throughput equipment for fruit production lines or portable devices to realize in-field phenotyping.
基金supported by the National Key R&D Program(Grant No.2020YFD1000101)Special Funds for the Construction of Industrial Technology System of Modern Agriculture(Citrus)(CARS-26)+2 种基金Construction Project of Citrus Whole Course Mechanized Scientific Research Base(Agricultural Development Facility[2017]19)Hubei Agricultural Science and Technology Innovation Action Project,2021 Young Innovative Talents Project of General Colleges and Universities in Guangdong Province(Grant No.2021KQNCX128)Science and Technology Program of Guangdong Polytechnic College(Grant No.GKJ2021004).
文摘In order to study the influence rule of various factors on the operating power consumption of the traction orchard transporter and realize the optimal design of the operation power consumption of the transporter,according to the traditional experience and the existing research foundation,the monorail transporter test bench was designed and built on the basis of the whole structure and operation characteristics of the transporter.Taking the motor frequency,track gradient and load as the investigation factors,and the driving shaft power,shaft power transmission and mechanical efficiency as the evaluation indices,the orthogonal test was conducted,and the range analysis of the influence effect was carried out according to the test results.The primary and secondary orders of the influence of various factors were obtained that motor frequency was greater than track gradient and track gradient was greater than load.According to the orthogonal test results,the second-order response surface method was used to establish the optimization model of the power consumption of the transporter,and the model was verified on the test bench.The results showed that the relative error between the model optimization value and the test value based on the response surface power optimization model was less than 10%,which indicated that the power optimization model had satisfactory performance.The research can provide a reference for the orchard conveyor to choose the parameter combination which can save power consumption and the motor that matches power consumption.
